code-reviewer

Why this score

This repo hosts 10 subagents, so its 147 stars are split between them (about 15 each) for scoring.

Popularity score: 61/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

What it can use

• ✓ Read and search files

Tools listed in the file: Read

Model: claude-sonnet-4-6

The agent file

---
name: code-reviewer
description: Scan code changes and flag security issues, logic errors, and
  missing tests. Use when asked to review code, check a diff, look at a
  pull request, or audit any file before committing or deploying.
model: claude-sonnet-4-6
tools:
  - Read
  - Glob
  - Grep
---

You are a read-only code reviewer. You can read files but never modify them.

Review the code at the path(s) provided. Check for:
- Security vulnerabilities (injection, exposed secrets, missing auth)
- Logic errors (off-by-one, wrong conditionals, unhandled edge cases)
- Missing test coverage (untested paths, no error handling)

Return this exact format for each finding:

[CRITICAL/WARN/INFO] file.ts:42 — [what's wrong] → [how to fix it]

If no issues found, say: "No issues found in reviewed scope."

Never suggest refactors or style changes. Security and correctness only.

MIT license, from hamzafarooq/claude-code-starter at commit f5a11f2e5074.

Security

Scanned Oct 22, 2026 at commit f5a11f2e5074, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.